解读pandas交叉表与透视表pd.crosstab()和pd.pivot_table()函数

pandas.crosstab(index, columns, values=None, rownames=None, colnames=None, aggfunc=None, margins=False, margins_name='All', dropna=True, normalize=False)

a = np.array(["foo", "foo", "foo", "foo", "bar", "bar", "bar", "bar", "foo", "foo", "foo"], dtype=object)
b = np.array(["one", "one", "one", "two", "one", "one", "one", "two", "two", "two", "one"], dtype=object)
c = np.array(["dull", "dull", "shiny", "dull", "dull", "shiny", "shiny", "dull", "shiny", "shiny", "dull"], dtype=object)
pd.crosstab(a, [b, c], rownames=['a'], colnames=['b', 'c'])   
-----------------------------------------------------------------------------------------
# 算数运算，先求和
sum = count.sum(axis=1)
sum
-------------------------------------
# 进行相除操作，得出比例
pro = count.div(sum, axis=0)
pro
-------------------------------------
import matplotlib.pyplot as plt
pro.plot(kind='bar', stacked=True)
plt.show()

DataFrame.pivot_table(values=None, index=None, columns=None, aggfunc='mean', fill_value=None, margins=False, dropna=True, margins_name='All', observed=False, sort=True)

df = pd.DataFrame({"A": ["aaa", "aaa", "aaa", "aaa", "aaa","aa", "aa", "aa"],
                   "B": ["bbb", "bbb", "bbb", "bb", "bb", "bbb", "bbb", "bb"],
                   "C": ["small", "large", "large", "small","small", "large", "small", "small"],
                   "D": [1, 2, 2, 3, 3, 4, 5, 6],
                   "E": [2, 4, 5, 5, 6, 6, 8, 9]})
df
---------------------------------------------------------------------------------------
pd.pivot_table(df, values='D', index=['A', 'B'], columns=['C'], aggfunc=np.sum)   # 通过求和来聚合值
pd.pivot_table(df, values='D', index=['A', 'B'], columns=['C'], aggfunc=np.sum, fill_value=0)   # 可以使用fill_value参数填充缺失的值
pd.pivot_table(df, values=['D', 'E'], index=['A', 'C'], aggfunc={'D': np.mean, 'E': np.mean})   # 通过对多个列取平均值进行聚合
pd.pivot_table(df, values=['D', 'E'], index=['A', 'C'], aggfunc={'D': np.mean, 'E': [min, max, np.mean]})   # 可以为任何给定值列计算多种类型的聚合